If you want to learn: don't use these models to do the things for you. Do use these models to learn.

LLMs might not the best teachers in the world but they're available right there and then when you have a question. Don't take their answers for granted and test them. Ask to teach you the correct terms for things you don't know yet, so you can ask better questions.

There has never been a better time to learn. You don't have to learn in the same way your predecessors did. You can learn faster and better, but must be vigilant you're not fooling yourself.

I remember the days of using books, having to follow the code bits in the book as I typed them. I don't remember diddly squat about it. Same from years of stack overflow. I'd just alt-tab 12 times, read the comments, then read another answer, assess the best answer. Massive waste of time.

Use all the technology you have at your hands I say. But be sure to understand what you auto-completed. If not, stop and learn.

If i use google maps to find my way around, i'm faster by a lot. I also do remember things despite google maps doing the work for me.

Use Code assistent as much as possible but make sure to read and understand what you get and try to write it yourself even if you just write it from a second window.

In this age and pace, writing code will change relevant in the next few years anyway

On the flip side, I've now found that getting AI to kick the tires on something I'm not super well versed in, helps me figure out how it works. But that's only because I understand how other things work.

If you're going to use AI in your learning, I think the best way you can do that is ask it to give you an example, or an incomplete implementation. Then you can learn in bits while still getting things done.

You put yourself at a significant disadvantage by not availing yourself of an infinitely patient, non-judgemental, and thoroughly well read tutor/coach.

You can get it to provide feedback on code quality, suggest refractors and its reasoning (with the explanation rather than the full solution), basically treating it as an always available study group.

There is probably room for a course or book on a methodology that allows students to engage in this practice, or models with prompts that forbid straight completion and just provide help aimed at students.

However the above advice for essays doesn't include not looking at textbooks or papers - just not to blindly copy.

So perhaps you should use coding assistents - but always in a mode where you use as a source to write yourself rather than cut and paste/direct editing.

But, exercise pressure in courses will probably increase to recalibrate for the difficulty level. I feel LLMs would make you make assignments so much faster I don't think you can not use it.

However, if - like 99% of software developers in the workforce - your goal is to work on software until you earn enough that you no longer have to, then ignore this awful advice and focus on learning the tools that are becoming ubiquitous and mandatory is most roles.

Otherwise you are pre-assigning yourself to irrelevance, equivalent to programmers refusing to use operating systems, compilers, runtimes, etc.

Data included in their training by default. You’ll need to opt-out.

Particularly, "Data excluded from training by default" is not available in the free and first paid tier.

Google was obviously irked that Microsoft got all this juicy training data since everyone is on their walled git garden, and tried to come up with a way to also dip some fingers into said data.

You should see the reviews in the JetBrains plugin page: https://plugins.jetbrains.com/plugin/24198-gemini-code-assis...

People are all so "shut up and take my money", but the bloody thing won't even sign them in.

But it's still in beta, right? Perhaps it'll start working in a couple more months.

I still feel more comfortable with the chat interface where I talk to LLM and make it generate the code that I end up putting together in a dumb editor because I'm still writing code for human based analysis that will be interpreted by machine and my claim is that if the code is actually to be written by machine for the consumption of a machine, then the human should be out of the code creation loop completely and fully assume the role of someone who demands stuff and knows when its done right and doesn't bother with the code itself.

I agree that it makes sense to use these currently but IMHO the ultimate programming will be human readable code-free, instead the AI will create a representation of the algorithm we need and will execute around it.

Like having an idea, for example if you need to program a robot vacuum cleaner you should be able to describe how you describe it to behave and the AI will create an algorithm(an idea, like "let's turn when bump into a wall then try again") and constantly tweak it and tend it. We wouldn't be directly looking at the code the AI wrote, instead we can test it and find edge cases that a machine maybe wouldn't predict(i.e. the cat sits on the robot and blocking the sensors).